Unsupervised SFQ-Based Spiking Neural Network

TL;DR

This paper demonstrates an ultra-fast, energy-efficient SFQ-based spiking neural network with innovative plasticity, threshold regulation, and winner-take-all mechanisms, validated through high-level modeling and circuit simulation.

Contribution

It introduces novel SFQ-based SNN components and mechanisms, including spike-timing-dependent plasticity, adaptive threshold regulation, and winner-take-all, advancing neuromorphic computing with superconducting technology.

Findings

Achieved ultra-fast switching with low energy per activity.

Successfully integrated novel mechanisms into high-level models.

Validated circuit functionality through simulation.

Abstract

Single Flux Quantum (SFQ) technology represents a groundbreaking advancement in computational efficiency and ultra-high-speed neuromorphic processing. The key features of SFQ technology, particularly data representation, transmission, and processing through SFQ pulses, closely mirror fundamental aspects of biological neural structures. Consequently, SFQ-based circuits emerge as an ideal candidate for realizing Spiking Neural Networks (SNNs). This study presents a proof-of-concept demonstration of an SFQ-based SNN architecture, showcasing its capacity for ultra-fast switching at remarkably low energy consumption per output activity. Notably, our work introduces innovative approaches: (i) We introduce a novel spike-timing-dependent plasticity mechanism to update synapses and to trace spike-activity by incorporating a leaky non-destructive readout circuit. (ii) We propose a novel method to dynamically regulate the threshold behavior of leaky integrate and fire superconductor neurons, enhancing the adaptability of our SNN architecture. (iii) Our research incorporates a novel winner-take-all mechanism, aligning with practical strategies for SNN development and enabling effective decision-making processes. The effectiveness of these proposed structural enhancements is evaluated by integrating high-level models into the BindsNET framework. By leveraging BindsNET, we model the online training of an SNN, integrating the novel structures into the learning process. To ensure the robustness and functionality of our circuits, we employ JoSIM for circuit parameter extraction and functional verification through simulation.